Cover Image

GRAPHTEXTACK: A Realistic Black-Box Node Injection Attack on LLM-Enhanced GNNs

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Ma, Jiaji, Trivedi, Puja, Koutra, Danai
Format:	Preprint
Published:	2025
Subjects:	Cryptography and Security Machine Learning
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Label Inference Attacks against Node-level Vertical Federated GNNs
by: Arazzi, Marco, et al.
Published: (2023)

Black-Box Privacy Attacks on Shared Representations in Multitask Learning
by: Abascal, John, et al.
Published: (2025)

BruSLeAttack: A Query-Efficient Score-Based Black-Box Sparse Adversarial Attack
by: Vo, Viet Quoc, et al.
Published: (2024)

Adaptive Attacks Break Defenses Against Indirect Prompt Injection Attacks on LLM Agents
by: Zhan, Qiusi, et al.
Published: (2025)

A Multi-Agent LLM Defense Pipeline Against Prompt Injection Attacks
by: Hossain, S M Asif, et al.
Published: (2025)

Tricking Retrievers with Influential Tokens: An Efficient Black-Box Corpus Poisoning Attack
by: Wang, Cheng, et al.
Published: (2025)

Distributional Black-Box Model Inversion Attack with Multi-Agent Reinforcement Learning
by: Bao, Huan, et al.
Published: (2024)

PIShield: Detecting Prompt Injection Attacks via Intrinsic LLM Features
by: Zou, Wei, et al.
Published: (2025)

Certifiable Black-Box Attacks with Randomized Adversarial Examples: Breaking Defenses with Provable Confidence
by: Hong, Hanbin, et al.
Published: (2023)

Understanding GNNs and Homophily in Dynamic Node Classification
by: Ito, Michael, et al.
Published: (2025)

Dissecting the Black Box: Circuit-Level Analysis of LLM Vulnerability Detection
by: Atiiq, Syafiq Al, et al.
Published: (2026)

AgentDojo: A Dynamic Environment to Evaluate Prompt Injection Attacks and Defenses for LLM Agents
by: Debenedetti, Edoardo, et al.
Published: (2024)

Fine-tuning is Not Fine: Mitigating Backdoor Attacks in GNNs with Limited Clean Data
by: Zhang, Jiale, et al.
Published: (2025)

AttackGNN: Red-Teaming GNNs in Hardware Security Using Reinforcement Learning
by: Gohil, Vasudev, et al.
Published: (2024)

Black-Box Adversarial Attacks on LLM-Based Code Completion
by: Jenko, Slobodan, et al.
Published: (2024)

Auditing Differential Privacy in the Black-Box Setting
by: Shi, Kaining, et al.
Published: (2025)

Counter-Samples: A Stateless Strategy to Neutralize Black Box Adversarial Attacks
by: Bokobza, Roey, et al.
Published: (2024)

Poisoning the Watchtower: Prompt Injection Attacks Against LLM-Augmented Security Operations Through Adversarial Log Content
by: Pandey, Rohan, et al.
Published: (2026)

SurvAttack: Black-Box Attack On Survival Models through Ontology-Informed EHR Perturbation
by: Kerdabadi, Mohsen Nayebi, et al.
Published: (2024)

Collective Certified Robustness against Graph Injection Attacks
by: Lai, Yuni, et al.
Published: (2024)

Black-Box Detection of Language Model Watermarks
by: Gloaguen, Thibaud, et al.
Published: (2024)

Revisiting the LiRA Membership Inference Attack Under Realistic Assumptions
by: Jebreel, Najeeb, et al.
Published: (2026)

Universal Black-Box Reward Poisoning Attack against Offline Reinforcement Learning
by: Xu, Yinglun, et al.
Published: (2024)

Prompt-Induced Over-Generation as Denial-of-Service: A Black-Box Attack-Side Benchmark
by: Manu, et al.
Published: (2025)

Query-Based and Unnoticeable Graph Injection Attack from Neighborhood Perspective
by: Liu, Chang, et al.
Published: (2025)

GNNBleed: Inference Attacks to Unveil Private Edges in Graphs with Realistic Access to GNN Models
by: Song, Zeyu, et al.
Published: (2023)

The Challenge of Identifying the Origin of Black-Box Large Language Models
by: Yang, Ziqing, et al.
Published: (2025)

Tree of Attacks: Jailbreaking Black-Box LLMs Automatically
by: Mehrotra, Anay, et al.
Published: (2023)

Benchmarking GNNs Using Lightning Network Data
by: Feichtinger, Rainer, et al.
Published: (2024)

Neural Exec: Learning (and Learning from) Execution Triggers for Prompt Injection Attacks
by: Pasquini, Dario, et al.
Published: (2024)

AttackLLM: LLM-based Attack Pattern Generation for an Industrial Control System
by: Ahmed, Chuadhry Mujeeb
Published: (2025)

Targeted Data Poisoning for Black-Box Audio Datasets Ownership Verification
by: Bouaziz, Wassim, et al.
Published: (2025)

Nearly Tight Black-Box Auditing of Differentially Private Machine Learning
by: Annamalai, Meenatchi Sundaram Muthu Selva, et al.
Published: (2024)

Attention-Enhanced Graph Filtering for False Data Injection Attack Detection and Localization
by: Abdulin, Ruslan, et al.
Published: (2026)

Kov: Transferable and Naturalistic Black-Box LLM Attacks using Markov Decision Processes and Tree Search
by: Moss, Robert J.
Published: (2024)

Backdoored Retrievers for Prompt Injection Attacks on Retrieval Augmented Generation of Large Language Models
by: Clop, Cody, et al.
Published: (2024)

Design Patterns for Securing LLM Agents against Prompt Injections
by: Beurer-Kellner, Luca, et al.
Published: (2025)

GenTel-Safe: A Unified Benchmark and Shielding Framework for Defending Against Prompt Injection Attacks
by: Li, Rongchang, et al.
Published: (2024)

SemBind: Binding Diffusion Watermarks to Semantics Against Black-Box Forgery Attacks
by: Zhang, Xin, et al.
Published: (2026)

REALISTA: Realistic Latent Adversarial Attacks that Elicit LLM Hallucinations
by: Liang, Buyun, et al.
Published: (2026)